@slamb2k/mad-skills 2.0.15 → 2.0.16

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "mad-skills",
   "description": "AI-assisted planning, development and governance tools",
-  "version": "2.0.15",
+  "version": "2.0.16",
   "author": {
     "name": "slamb2k",
     "url": "https://github.com/slamb2k"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@slamb2k/mad-skills",
-  "version": "2.0.15",
+  "version": "2.0.16",
   "description": "Claude Code skills collection — planning, development and governance tools",
   "type": "module",
   "repository": {

package/skills/brace/SKILL.md

@@ -2,7 +2,7 @@
 name: brace
 description: 'Initialize any project directory with the GOTCHA/BRACE framework for agentic AI systems. Creates the 6-layer structure (Goals, Orchestration, Tools, Context, Hard prompts, Args), BRACE build methodology, and a project CLAUDE.md. Recommends claude-mem for persistent memory. Idempotent — safe to run on existing projects. Triggers: "init gotcha", "setup brace", "brace", "initialize framework", "bootstrap gotcha".'
 argument-hint: "[--no-brace] [--force]"
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
 # Brace - GOTCHA/BRACE Framework Bootstrap

package/skills/build/SKILL.md

@@ -2,7 +2,7 @@
 name: build
 description: Context-isolated feature development pipeline. Takes a detailed design/plan as argument and executes the full feature-dev lifecycle (explore, question, architect, implement, review, ship) inside subagents so the primary conversation stays compact. Use when you have a well-defined plan and want autonomous execution with minimal context window consumption.
 argument-hint: <detailed design/plan to implement> [--skip-questions] [--skip-review] [--no-ship] [--parallel-impl]
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
 # Build - Context-Isolated Feature Development
@@ -60,6 +60,7 @@ Before starting, check all dependencies in this table:
 | Dependency | Type | Check | Required | Resolution | Detail |
 |-----------|------|-------|----------|------------|--------|
 | ship | skill | `.claude/skills/ship/SKILL.md` | yes | stop | Install with: npx skills add slamb2k/mad-skills --skill ship |
+| prime | skill | `.claude/skills/prime/SKILL.md` | no | fallback | Context loading; falls back to manual CLAUDE.md/goals scan |
 | feature-dev:code-explorer | agent | — | no | fallback | Uses general-purpose agent |
 | feature-dev:code-architect | agent | — | no | fallback | Uses general-purpose agent |
 | feature-dev:code-reviewer | agent | — | no | fallback | Uses general-purpose agent |
@@ -76,7 +77,10 @@ For each row, in order:
 4. After all checks: summarize what's available and what's degraded
 
 1. Capture **PLAN** (the user's argument) and **FLAGS**
-2. Detect project type using `references/project-detection.md` to populate
+2. **Load project context** — invoke `/prime` to load domain-specific context
+   (CLAUDE.md, goals, specs, memory). If /prime is unavailable, fall back to
+   manually scanning CLAUDE.md and goals/ directory.
+3. Detect project type using `references/project-detection.md` to populate
    **PROJECT_CONFIG** (language, test_runner, test_setup)
 3. Check for outstanding questions from previous work:
    - Search CLAUDE.md for a "Known Issues" or "Open Questions" section

package/skills/distil/SKILL.md

@@ -2,7 +2,7 @@
 name: distil
 description: Generate multiple unique web design variations for any website or web application. Accepts site specifications from a file (--spec path) or pasted text block. Creates a Vite + React + TypeScript + Tailwind project with Bun and produces N different creative designs accessible at /1, /2, /3, etc. Use when prototyping or exploring design directions for any web interface.
 argument-hint: <count> --port <port> [--spec <path>] [--favorites <1,2,3>]
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, WebFetch, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, WebFetch, AskUserQuestion
 ---
 
 # Distil - Design Variation Generator

package/skills/dock/SKILL.md

@@ -64,6 +64,7 @@ Before starting, check dependencies:
 |-----------|------|-------|----------|------------|--------|
 | docker | cli | `docker --version` | no | ask | Needed for local build verification; skip verify phase if absent |
 | git | cli | `git --version` | yes | stop | Install from https://git-scm.com |
+| sync | skill | `.claude/skills/sync/SKILL.md` | no | fallback | Repo sync; falls back to manual git pull |
 
 For each row:
 1. Run the Check command
@@ -73,6 +74,14 @@ For each row:
 
 ---
 
+## Phase 0: Sync
+
+Invoke `/sync` to ensure the working tree is up to date with origin/main before
+scanning. If /sync is unavailable, run `git pull` manually. This prevents
+generating pipelines against stale code.
+
+---
+
 ## Phase 1: Detection
 
 Launch an **Explore subagent** to scan the codebase and produce a DETECTION_REPORT.

package/skills/keel/SKILL.md

@@ -68,6 +68,7 @@ Before starting, check dependencies:
 | Dependency | Type | Check | Required | Resolution | Detail |
 |-----------|------|-------|----------|------------|--------|
 | git | cli | `git --version` | yes | stop | Install from https://git-scm.com |
+| sync | skill | `.claude/skills/sync/SKILL.md` | no | fallback | Repo sync; falls back to manual git pull |
 | terraform | cli | `terraform --version` | no | fallback | Detected if user wants Terraform; suggest install from https://terraform.io |
 | az | cli | `az --version` | no | fallback | Needed for Bicep; suggest install from https://aka.ms/install-azure-cli |
 | pulumi | cli | `pulumi version` | no | fallback | Detected if user wants Pulumi; suggest install from https://pulumi.com |
@@ -78,6 +79,13 @@ Skip checks for tools not being used.
 
 ---
 
+## Phase 0: Sync
+
+Invoke `/sync` to ensure the working tree is up to date with origin/main.
+Falls back to `git pull` if /sync is unavailable.
+
+---
+
 ## Phase 1: Detection
 
 Launch an **Explore subagent** to scan the codebase for existing infrastructure.
@@ -484,11 +492,7 @@ If /keel detects it has been run before (existing `infra/` directory):
 
 ## Integration Points
 
-- **/dock**: /keel provisions what /dock deploys to. After /keel applies, /dock's
-  pipelines use the outputs (registry URL, compute endpoints) as deployment targets.
-  If /dock has already run, /keel reads `deploy/environments.json` to know what
-  platforms to provision.
-- **/rig**: When /rig runs after /keel, it can detect `infra/` and ensure the
-  IaC pipeline is wired into the CI workflow.
-- **/ship**: /ship's merge triggers the IaC apply pipeline, which then triggers
-  /dock's deployment pipeline. The chain: merge → apply infra → deploy containers.
+- **/dock**: /keel provisions what /dock deploys to. /dock pipelines consume
+  the outputs (registry URL, compute endpoints) as deployment targets.
+- **/rig**: Detects `infra/` and wires IaC pipeline into CI workflow.
+- **/ship**: Merge triggers IaC apply → /dock deploy chain.

package/skills/manifest.json

@@ -1,5 +1,5 @@
 {
-  "generated": "2026-03-09T16:34:19.534Z",
+  "generated": "2026-03-09T17:01:26.694Z",
   "count": 10,
   "skills": [
     {
@@ -16,7 +16,7 @@
       "name": "build",
       "directory": "build",
       "description": "Context-isolated feature development pipeline. Takes a detailed design/plan as argument and executes the full feature-dev lifecycle (explore, question, architect, implement, review, ship) inside subagents so the primary conversation stays compact. Use when you have a well-defined plan and want autonomous execution with minimal context window consumption.",
-      "lines": 328,
+      "lines": 332,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": false,
@@ -36,7 +36,7 @@
       "name": "dock",
       "directory": "dock",
       "description": ">- Generate container-based release pipelines that build once and promote immutable artifacts through environments (dev → staging → prod). Detects your stack, interviews for infrastructure choices, then outputs deterministic CI/CD files (Dockerfile, workflows, deployment manifests) that run without an LLM. Use when setting up deployment pipelines, containerizing an app, creating release workflows, or connecting CI to container-friendly infrastructure (Azure Container Apps, AWS Fargate, Google Cloud Run, Kubernetes, Dokku, Coolify, CapRover, etc.).",
-      "lines": 349,
+      "lines": 358,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": false,
@@ -46,7 +46,7 @@
       "name": "keel",
       "directory": "keel",
       "description": ">- Generate Infrastructure as Code (IaC) pipelines that provision the cloud and container infrastructure your app deploys to. Interview-driven: detects your stack and cloud provider, then outputs deterministic IaC files (Terraform, Bicep, Pulumi, or CDK) plus CI/CD pipelines that plan on PR and apply on merge. Use when setting up cloud infrastructure, provisioning container registries, databases, networking, DNS, or any infrastructure that containers deploy onto. Designed to run before /dock — /keel lays the infrastructure, /dock deploys to it.",
-      "lines": 495,
+      "lines": 499,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": false,
@@ -55,8 +55,8 @@
     {
       "name": "prime",
       "directory": "prime",
-      "description": "\"Load project context before implementing features or making architectural decisions. Invoke proactively when starting significant work on DexAI. Supports domain-specific context loading: security (vault, RBAC, audit), routing (OpenRouter, model selection), adhd (design principles, RSD-safe), dashboard (frontend, backend, API), office (OAuth, email, calendar), memory (context capture, commitments), tasks (decomposition, friction-solving), channels (Telegram, Discord, Slack).\"",
-      "lines": 108,
+      "description": "\"Load project context before implementing features or making architectural decisions. Invoke proactively at the start of significant work on any project. Scans CLAUDE.md, README, goals/, specs/, docs/, and source structure to build a context summary. Supports optional domain hints to focus on specific areas of the codebase. Use when you need project conventions, architecture understanding, or domain context before coding.\"",
+      "lines": 113,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": false,
@@ -66,7 +66,7 @@
       "name": "rig",
       "directory": "rig",
       "description": "'Idempotently bootstrap any repository with standard development tools, hooks, and workflows. Use when starting work on a new repo, onboarding to an existing project, or ensuring a repo has proper CI/CD setup. Configures: git hooks (lefthook), commit message templates, PR templates, and GitHub Actions for lint/format/type-check/build. Prompts for user confirmation before changes. Triggers: \"bootstrap repo\", \"setup hooks\", \"configure CI\", \"rig\", \"standardize repo\".'",
-      "lines": 197,
+      "lines": 206,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": true,
@@ -86,7 +86,7 @@
       "name": "speccy",
       "directory": "speccy",
       "description": "Deep-dive interview skill for creating comprehensive specifications. Reviews existing code and docs, then interviews the user through multiple rounds of targeted questions covering technical implementation, UI/UX, concerns, and tradeoffs. Produces a structured spec via create-specification. Use when starting a new feature, system, or major change that needs a spec.",
-      "lines": 166,
+      "lines": 170,
       "hasScripts": false,
       "hasReferences": true,
       "hasAssets": false,

package/skills/prime/SKILL.md

@@ -1,8 +1,8 @@
 ---
 name: prime
-description: "Load project context before implementing features or making architectural decisions. Invoke proactively when starting significant work on DexAI. Supports domain-specific context loading: security (vault, RBAC, audit), routing (OpenRouter, model selection), adhd (design principles, RSD-safe), dashboard (frontend, backend, API), office (OAuth, email, calendar), memory (context capture, commitments), tasks (decomposition, friction-solving), channels (Telegram, Discord, Slack)."
-argument-hint: security, routing, adhd, dashboard, office, memory, tasks, channels (comma-separated)
-allowed-tools: Read, Glob, Grep, LS
+description: "Load project context before implementing features or making architectural decisions. Invoke proactively at the start of significant work on any project. Scans CLAUDE.md, README, goals/, specs/, docs/, and source structure to build a context summary. Supports optional domain hints to focus on specific areas of the codebase. Use when you need project conventions, architecture understanding, or domain context before coding."
+argument-hint: "[domain hints: comma-separated directory or topic names to focus on]"
+allowed-tools: Read, Glob, Grep, LS, Agent
 ---
 
 # Prime - Project Context Loader
@@ -39,8 +39,9 @@ subagent — the primary thread only sees a structured PRIME_REPORT.
 
 ## Step 1: Parse Arguments
 
-Extract domain hints from the request (comma-separated). Valid domains are
-listed in `references/domains.md`. If no domain specified, load core context only.
+Extract domain hints from the request (comma-separated). These are directory
+names or topic keywords to focus the context scan on. If no domain specified,
+load core context only (CLAUDE.md, README, goals/, specs/).
 
 ## Step 2: Load Context via Subagent
 
@@ -64,15 +65,19 @@ Limit PRIME_REPORT to 30 lines maximum.
 
 ## Core Files (always load)
 
-1. CLAUDE.md — System handbook, operating procedures
-2. goals/manifest.md — Phase status, available goals, project roadmap
-3. tools/manifest.md — Available tools and their locations
+1. CLAUDE.md — Project conventions, architecture, instructions
+2. README.md — Project overview, setup, usage
+3. goals/ or specs/ — Project goals, specs, roadmap (scan directory if present)
+4. docs/ — Documentation directory (scan if present)
 
-If CLAUDE.md is missing, record as NOT FOUND and continue.
+If a file is missing, record as NOT FOUND and continue.
 
 ## Domain Files
 
-{For each requested domain, list files from references/domains.md}
+{For each requested domain hint, use Glob to find relevant files:}
+- Search for directories matching the hint name (e.g., "auth" → src/auth/, lib/auth/)
+- Search for files matching *{hint}*.md, *{hint}*.yaml, *{hint}*.json
+- Read the most relevant matches (max 5 files per domain)
 
 For each file:
 - If it exists: read and summarise (2-3 lines max per domain)

package/skills/prime/references/domains.md

@@ -1,38 +1,35 @@
-# Domain-to-File Mapping
+# Domain Context Resolution
 
-Each domain lists the files/directories to load for that context area.
-Paths are relative to the project root.
+When domain hints are provided, resolve them to files using these strategies
+(in priority order). Stop at the first strategy that produces results.
 
-## security
-- `args/security.yaml`
-- `tools/security/` (list directory)
+## Resolution Strategy
 
-## routing
-- `args/routing.yaml`
-- `tools/agent/model_router/ROUTING_ARCHITECTURE.md`
+1. **Exact directory match** — Look for a directory named `{hint}/` in common
+   locations: `src/`, `lib/`, `app/`, `packages/`, `services/`, project root
+2. **File pattern match** — Glob for `**/*{hint}*.md`, `**/*{hint}*.yaml`,
+   `**/*{hint}*.json` (exclude node_modules, .git, dist, build)
+3. **Config/docs match** — Check `docs/{hint}.md`, `docs/{hint}/`,
+   `config/{hint}.*`, `.{hint}rc`, `{hint}.config.*`
 
-## adhd
-- `context/adhd_design_principles.md`
-- `args/adhd_mode.yaml`
+## Common Domain Hints
 
-## dashboard
-- `args/dashboard.yaml`
-- `tools/dashboard/backend/routes/` (list directory)
-- `tools/dashboard/frontend/app/` (list directory)
+These are examples — any directory or topic name works as a hint:
 
-## office
-- `args/office_integration.yaml`
-- `tools/office/` (list directory)
+| Hint | Likely Locations |
+|------|-----------------|
+| auth | src/auth/, lib/auth/, middleware/auth.* |
+| api | src/api/, routes/, controllers/ |
+| db, database | src/db/, prisma/, migrations/, models/ |
+| infra | infra/, terraform/, bicep/, deploy/ |
+| frontend | src/components/, src/pages/, app/ |
+| backend | src/server/, src/services/, api/ |
+| config | config/, .env.example, settings/ |
+| test | tests/, __tests__/, spec/, cypress/ |
 
-## memory
-- `args/memory.yaml`
-- `args/working_memory.yaml`
-- `tools/memory/` (list directory)
+## Output
 
-## tasks
-- `args/task_engine.yaml`
-- `tools/tasks/` (list directory)
-
-## channels
-- `args/channels.yaml`
-- `tools/channels/` (list directory)
+For each resolved domain, include in PRIME_REPORT:
+- Directory/file paths found
+- 2-3 line summary of what was found
+- Key patterns or conventions observed

package/skills/rig/SKILL.md

@@ -2,7 +2,7 @@
 name: rig
 description: 'Idempotently bootstrap any repository with standard development tools, hooks, and workflows. Use when starting work on a new repo, onboarding to an existing project, or ensuring a repo has proper CI/CD setup. Configures: git hooks (lefthook), commit message templates, PR templates, and GitHub Actions for lint/format/type-check/build. Prompts for user confirmation before changes. Triggers: "bootstrap repo", "setup hooks", "configure CI", "rig", "standardize repo".'
 argument-hint: --skip-system-check (optional)
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
 # Rig - Repository Bootstrap
@@ -50,6 +50,7 @@ Before starting, check all dependencies in this table:
 | Dependency | Type | Check | Required | Resolution | Detail |
 |-----------|------|-------|----------|------------|--------|
 | git | cli | `git --version` | yes | stop | Install from https://git-scm.com |
+| sync | skill | `.claude/skills/sync/SKILL.md` | no | fallback | Repo sync; falls back to manual git pull |
 | lefthook | npm | `npx lefthook --help` | yes | install | `npm install -g lefthook` |
 | gh | cli | `gh --version` | yes | url | https://cli.github.com |
 
@@ -66,6 +67,14 @@ For each row, in order:
 
 ---
 
+## Phase 0: Sync
+
+Invoke `/sync` to ensure the working tree is up to date with origin/main before
+bootstrapping. If /sync is unavailable, run `git pull` manually. This prevents
+rigging against stale repo state.
+
+---
+
 ## Phase 1: System Requirements Check
 
 Launch **Bash subagent** (haiku — simple checks):

package/skills/ship/SKILL.md

@@ -2,7 +2,7 @@
 name: ship
 description: "Ship changes through the full PR lifecycle. Use after completing feature work to commit, push, create PR, wait for checks, and merge. Handles the entire workflow: syncs with main, creates feature branch if needed, groups commits logically with semantic messages, creates detailed PR, monitors CI, fixes issues, squash merges, and cleans up. Invoke when work is ready to ship."
 argument-hint: --pr-only, --no-squash, --keep-branch (optional flags)
-allowed-tools: Bash, Read, Glob, Grep, Skill
+allowed-tools: Bash, Read, Glob, Grep, Agent, Skill
 ---
 
 # Ship - Full PR Lifecycle

package/skills/ship/references/stage-prompts.md

@@ -294,20 +294,12 @@ BRANCH_FLAGS: {--delete-branch (default) | omit if --keep-branch}
          --delete-source-branch $DELETE_BRANCH
      fi
 
-2. **Sync local {DEFAULT_BRANCH}**
-   git checkout {DEFAULT_BRANCH}
-   git pull {REMOTE} {DEFAULT_BRANCH}
+2. **Sync local repository**
+   Invoke `/sync` to checkout {DEFAULT_BRANCH}, pull latest changes, restore
+   any stashed work, and clean up merged branches. This replaces manual git
+   checkout/pull/fetch/prune — /sync handles all of it including stash restore.
 
-3. **Restore working state** (if there were stashed changes)
-   git stash pop (only if stash exists from Stage 1)
-
-4. **Cleanup stale branches**
-   git fetch --prune
-   for branch in $(git branch -vv | grep ': gone]' | awk '{print $1}'); do
-     git branch -d "$branch" 2>/dev/null
-   done
-
-5. **Report**
+3. **Report**
    MERGE_COMMIT=$(git rev-parse --short HEAD)
 
 ## Output Format

package/skills/speccy/SKILL.md

@@ -2,7 +2,7 @@
 name: speccy
 description: Deep-dive interview skill for creating comprehensive specifications. Reviews existing code and docs, then interviews the user through multiple rounds of targeted questions covering technical implementation, UI/UX, concerns, and tradeoffs. Produces a structured spec via create-specification. Use when starting a new feature, system, or major change that needs a spec.
 argument-hint: Goal, feature, or high-level description to specify
-allowed-tools: Bash, Read, Write, Edit, Glob, Grep, AskUserQuestion
+allowed-tools: Bash, Read, Write, Edit, Glob, Grep, Agent, AskUserQuestion
 ---
 
 # Speccy - Interview-Driven Specification Builder
@@ -47,6 +47,7 @@ Before starting, check all dependencies in this table:
 | Dependency | Type | Check | Required | Resolution | Detail |
 |-----------|------|-------|----------|------------|--------|
 | create-specification | skill | `~/.claude/skills/create-specification/SKILL.md` or `~/.agents/skills/create-specification/SKILL.md` | yes | ask | This skill is needed to format the final spec. Install with: `npx skills add slamb2k/mad-skills --skill create-specification` |
+| prime | skill | `.claude/skills/prime/SKILL.md` | no | fallback | Context loading; falls back to manual project scan |
 
 For each row, in order:
 1. Test file existence (check both paths for symlinked skills)
@@ -63,7 +64,10 @@ For each row, in order:
 Before asking any questions, build a thorough understanding of the project:
 
 1. **Capture GOAL** — the user's argument describing what needs to be specified
-2. **Scan the project**:
+2. **Load project context** — invoke `/prime` to load domain-specific context
+   (CLAUDE.md, goals, specs, memory). If /prime is unavailable, fall back to
+   the manual scan below.
+3. **Scan the project** (skip items already loaded by /prime):
    - Read `CLAUDE.md` if present (project conventions, structure, domain)
    - Read goal/spec manifests: `goals/manifest.md`, `spec/` directory
    - Scan existing specs and design docs for context